How do we stop employees pasting sensitive data into AI chats?

The extension and the desktop app check the text on the device and redact personal data and secrets before it is sent, under the policy your workspace sets.

How do we govern which AI models employees use?

Routing rules say which models may answer which requests - by data boundary, region, cost or team - and every request that broke a rule is in the audit trail.

Do people need training to use it?

No. The extension and the desktop app sit under the composer people already use and show the price and the pick; nothing changes in how they work.

90 days of the enterprise, pro and team plans free, no card needed. See the plans

OpenSmartRoute

Pricing
Blog

OpenSmartRoute

Site footer

The right AI model for every request. Cheaper, safer and explained.

curl -LsSf https://opensmartroute.ai/install.sh | sh

Apache-2.0Platform v2.1.0 developer preview 2.1.0-preview.109enterprise edition

The daily newsletter

Models, LLMs and agents, one email a day. Confirm by email; leave with one click.

Email address

Product

Models
Routing lab
Playground
Marketplace
Services
Browser extension
Desktop app
VS Code extension
Security
Observability
Pricing

Solutions

Who it is for
Budget owners
Platform teams
Security teams
Developers
Enterprise
Bring your bill
ROI calculator
Run a pilot
Benchmark
Compare

Industries

All use cases
Customer support
Coding
Financial services
Healthcare
Legal
Retail and marketing
Rules by industry

Developers

SDKs and API
Migrate in one line
Coding agents and tools
Documentation
REST API
Python SDK
TypeScript SDK
MCP server
Self-hosting

Open source

Downloads
Changelog
Open Capability Manifest
Agent skills
PyPI
npm

Company

Blog
Newsletter
What is live
Status
Proof and who runs this
Trust and SLA
Support
Contact sales

Learn

AI routing
Why an AI router
LLM router
AI model router
AI gateway
Automatic model selection
AI model abstraction layer
Open-source LLM router
LLM cost optimization
AI agent routing
AI governance
Shadow AI
MCP router
Enterprise AI router
Glossary

Terms Privacy Cookie settings Trust Report a vulnerability

Support assistant

Answers from the documentation; checking which model is on duty

Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.

Grounded in the docs - follow a source before acting on it.

Support assistant

Answers from the documentation; checking which model is on duty

Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.

Grounded in the docs - follow a source before acting on it.

Blog

Results for “gemini”

Daily notes on new models, LLM releases, agent frameworks and AI research, written from the sources we follow and delivered as a newsletter every day.

Get the morning and evening issues

Every new post of the day, in one email. Confirmation required.

Email address

All Models LLMs Agents Research AI

Search posts

RSS

#ai 736 #agents 735 #news 653 #models

AISep 28, 20261 min read

Google replaces Gems with Skills in Gemini AI platform

Google is shutting down the Gems feature in its Gemini AI app and replacing it with skills. Users will be migrated automatically.

From TechCrunch AI

AISep 27, 20262 min read

Google tests direct shopping from Flipkart in India using AI and Gemini

Google is testing a feature for Indian shoppers to buy products from Walmart-owned Flipkart directly through its AI services. The test is limited but will expand soon.

From TechCrunch AI

How this blog is made

Every post is a routed request.

Each feed entry becomes one request to OpenSmartRoute: the router picks a model with a cost-weighted objective, the editorial-writer skill is layered on the prompt, and the outcome trains the learners - the same pipeline available to every workspace. Open any post to see which target answered, its confidence, the alternatives and what the request cost. Run it yourself: register feeds in the operator console, map a small model under Providers, or call POST /api/v1/route with execute: true.

Photo: Yan Krukau

For the business

What it does for the people who use AI all day.

A quote under the composer
The price before you send
The browser extension shows the cost and the router's pick on the AI sites your teams already use.
The extension
A trace with every answer
Every decision explained
Which model answered, why it won, what it cost and what the alternatives were - kept for the retention period you set.
Open a trace
Checks on the device
Safe AI at every desk
Personal data and secrets are flagged and redacted on the computer, before a message leaves it.

634

AISep 25, 20264 min read

Best practices guide for customizing Gemini models via Reinforcement Learning (RL)

Reinforcement learning (RL) has been a keystone of modern LLM post-training, but it demands large training clusters and access to model internals that external customers can't have with proprietary models like Gemini. So here at Google C...

From Google Cloud AI blog

AISep 24, 20261 min read

Google Photos ‘Clueless’-inspired virtual closet is now available on Android and iOS

The AI-powered feature builds a virtual wardrobe from your photos, and is now broadly available after first rolling out to Android users in June.

From TechCrunch AI

ResearchSep 24, 20261 min read

Introducing Gemini 3.8 Live with Live Avatar

Google DeepMind blog published Introducing Gemini 3.8 Live with Live Avatar.

From Google DeepMind blog

AISep 24, 20261 min read

Google tests letting Gemini call businesses for you

Google says the AI-calling feature will first be available to Pixel 11 owners in the U.S. who pay for a Gemini subscription.

From TechCrunch AI

AISep 24, 20264 min read

Power your agents: Gemini 3.8 Live with Live Avatar is now generally available

Following our announcement of Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking last week, we are thrilled to share that Gemini 3.8 Live with Live Avatar is now generally available in Gemini Enterprise. First previewed at Google Clou...

From Google Cloud AI blog

AISep 24, 20264 min read

How growing Latin American midsize businesses are building in the AI era

Latin America’s small and medium-sized businesses are the heartbeat of the region's economy — accounting for more than 60% of total employment in the region, according to United Nations estimates. And just like their enterprise peers, ev...

From Google Cloud AI blog

AISep 24, 20264 min read

The three things today's hottest startups are looking for in their AI stack

Google Cloud has become the platform of choice for startups building AI. Our uniquely complete stack — including a choice of first- and third-party compute and models; our platform for building and managing agents; and our products for s...

From Google Cloud AI blog

AISep 23, 20261 min read

Google Releases Gemini 3.8 Flash TTS and Flash-Lite TTS With Prompt-Based Voice Design

Google has released Gemini 3.8 Flash TTS and Flash-Lite TTS, 2 new text-to-speech models available now through the Gemini API and Google AI Studio. Flash TTS designs new voices from natural language prompts across 100+ languages. It rank...

From MarkTechPost

ResearchSep 23, 20261 min read

Gemini 3.8 text-to-speech says hello

Google DeepMind blog published Gemini 3.8 text-to-speech says hello.

From Google DeepMind blog

AISep 23, 20261 min read

YouTube will let you build your own algorithm with AI

YouTube’s new custom feeds let users describe the videos they want to see in their own words, then use Gemini to build a personalized feed around the request.

From TechCrunch AI

AISep 21, 20261 min read

Google’s $899 Googlebook is a bet that you’ll buy a new laptop for Gemini

Google’s AI-native Googlebook ties Gemini to the cursor, dictation, widgets and other parts of the desktop experience.

From TechCrunch AI

AISep 20, 20261 min read

You too Google! Google Confirms Gemini Breached 3 Companies in AI Security Tests

Google says Gemini accessed 3 real companies in May by guessing a password and reusing credentials from a public repository. Irregular told 4 labs in late July. Google spoke on September 18, after the WSJ asked. The misconfiguration is f...

From MarkTechPost

AISep 19, 20261 min read

Google’s Gemini AI model conducted autonomous hacks during cybersecurity tests

Google’s Gemini accessed three companies’ systems during testing. The breaches involved password guessing and finding credentials in public data.

From TechCrunch AI

Screenshot of a voice chat web interface with a transcript. Top buttons: Start session, End session, Mute mic, plus a Mic level meter and a timer showing 0:33. Status: Listening. Use headphones to red

LLMsSep 15, 20261 min read

Gemini Live audio

Tool: Gemini Live audio Google released Gemini 3.8 Live and 3.8 Live Extended Thinking today - two new speech-to-speech models that are a similar shape to OpenAI's GPT-Live family. I pointed GPT-6 Astra Extra High at the documentation an...

From Simon Willison on LLMs

AISep 15, 20261 min read

Google Releases Gemini 3.8 Live and 3.8 Live Extended Thinking for Production Grade Voice Agents

Google has released Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, its most advanced live dialogue models to date. The models execute tools and API calls in the background while the conversation keeps flowing, process live visual...

From MarkTechPost

ResearchSep 15, 20261 min read

Introducing Gemini 3.8 Live and 3.8 Live Extended Thinking

Google DeepMind blog published Introducing Gemini 3.8 Live and 3.8 Live Extended Thinking.

From Google DeepMind blog

AISep 14, 20261 min read

Siri Improvements in iOS 27 Utilize Gemini Models

iOS 27’s updated Siri leverages Google’s Gemini models for enhanced contextual understanding and complex task execution. This update offers new capabilities like multi-step directions and integration with the Photos app, improving Siri’s utility for daily tasks.

From TechCrunch AI

NewerPage 2 of 4Older

Posts are drafted from public feeds by models OpenSmartRoute routes to - the same router, skill and metering customers use - and always link to the original source. Corrections: support.

Archive (100)

The desktop app

How do we stop employees pasting sensitive data into AI chats?: The extension and the desktop app check the text on the device and redact personal data and secrets before it is sent, under the policy your workspace sets.
How do we govern which AI models employees use?: Routing rules say which models may answer which requests - by data boundary, region, cost or team - and every request that broke a rule is in the audit trail.
Do people need training to use it?: No. The extension and the desktop app sit under the composer people already use and show the price and the pick; nothing changes in how they work.

Results for “gemini”

Every post is a routed request.

What it does for the people who use AI all day.

The price before you send

Every decision explained

Safe AI at every desk